kubevirt_vmi_vcpu_wait_seconds_total is an IO specific metric.
The time a vCPU has to wait for IO.

The docs - https://docs.redhat.com/en/documentation/openshift_container_platform/4.16/html/virtualization/monitoring#virt-promql-vcpu-metrics_virt-prometheus-queries - do not mention this, but the should.

Instead of 
Returns the wait time (in seconds) for a virtual machine’s vCPU. Type: Counter. 

it should be
Returns the wait time (in seconds) on IO for a virtual machine’s vCPU. Type: Counter. 

4.16

always

1.
2.
3.